URL has been copied successfully!
False memories planted in ChatGPT give hacker persistent exfiltration channel – Information is key, but action opens the lock
URL has been copied successfully!

Information is key, but action opens the lock

False memories planted in ChatGPT give hacker persistent exfiltration channel

—

by

Andy Stern
in

Tags: , , ,

Emails, documents, and other untrusted content can plant malicious memories.

First seen on arstechnica.com

Jump to article: arstechnica.com/

Loading

Share via Email
Share on Facebook
Tweet on X (Twitter)
Share on Whatsapp
Share on LinkedIn
Share on Xing
Copy link

also interesting:

  1. What Is Phishing-Resistant MFA and How Does it Work?
  2. Hackers Install macOS Malware Using Weaponised Calendar Invites
  3. DNS Tunneling Used for Stealthy Scans and Email Tracking
  4. Hackers deliver popular crypto-miner through malicious email auto replies, researchers say